1 code implementation • 3 Apr 2024 • Sijie Zhao, Hao Chen, Xueliang Zhang, Pengfeng Xiao, Lei Bai, Wanli Ouyang
RSM is specifically designed to capture the global context of remote sensing images with linear complexity, facilitating the effective processing of large VHR images.
Ranked #1 on Road Segmentation on Massachusetts Roads Dataset (F1 metric)
Building change detection for remote sensing images Change Detection +1
no code implementations • 22 Feb 2024 • Changjiang Zhao, Shulin He, Xueliang Zhang
Speech enhancement aims to improve speech quality and intelligibility, especially in noisy environments where background noise degrades speech signals.
1 code implementation • 6 Feb 2024 • Pengming Feng, Mingjie Xie, Hongning Liu, Xuanjia Zhao, Guangjun He, Xueliang Zhang, Jian Guan
To this end, we propose a benchmark dataset for fine-grained Ship Instance Segmentation in Panchromatic satellite images, namely SISP, which contains 56, 693 well-annotated ship instances with four fine-grained categories across 10, 000 sliced images, and all the images are collected from SuperView-1 satellite with the resolution of 0. 5m.
1 code implementation • 4 Feb 2024 • Dilxat Muhtar, Zhenshi Li, Feng Gu, Xueliang Zhang, Pengfeng Xiao
Additionally, we introduce LHRS-Bench, a benchmark for thoroughly evaluating MLLMs' abilities in RS image understanding.
1 code implementation • 19 Nov 2023 • Sijie Zhao, Xueliang Zhang, Pengfeng Xiao, Guangjun He
We build a binary change detection model based on this strategy, and then validate and compare it with 18 state-of-the-art change detection methods on six datasets in three scenarios, including intraclass change detection datasets (CDD, SYSU), single-view building change detection datasets (WHU, LEVIR-CD, LEVIR-CD+) and a multiview building change detection dataset (NJDS).
Ranked #2 on Change Detection on WHU Building Dataset
1 code implementation • 19 Apr 2023 • Dilxat Muhtar, Xueliang Zhang, Pengfeng Xiao, Zhenshi Li, Feng Gu
We argue that this learning strategy is suboptimal in the realm of RS, since the required representations for different RS downstream tasks are often varied and complex.
no code implementations • 2 Dec 2022 • Pengjie Shen, Shulin He, Xueliang Zhang
Target speaker extraction is to extract the target speaker, specified by enrollment utterance, in an environment with other competing speakers.
no code implementations • 26 Jul 2021 • Jinjiang Liu, Xueliang Zhang
For dual-channel speech enhancement, it is a promising idea to design an end-to-end model based on the traditional array signal processing guideline and the manifold space of multi-channel signals.
no code implementations • 26 Mar 2021 • Hao Li, Xueliang Zhang, Guanglai Gao
Another way is to use an anchor speech, a short speech of the target speaker, to model the speaker identity.
no code implementations • 25 Oct 2020 • Shulin He, Hao Li, Xueliang Zhang
This paper introduces an improved target speaker extractor, referred to as Speakerfilter-Pro, based on our previous Speakerfilter model.
no code implementations • 2 Feb 2020 • Jingdong Li, HUI ZHANG, Xueliang Zhang, Changliang Li
We show that our model is able to improve the performance of model, compared with existing convolutional recurrent networks.
no code implementations • 20 Jun 2019 • Yue Gu, Zhihao Du, HUI ZHANG, Xueliang Zhang
To improve the robustness, a speech enhancement front-end is involved.
no code implementations • 4 Sep 2017 • Shasha Xia, Hao Li, Xueliang Zhang
In this paper, we use the optimal ratio mask as the training target of the deep neural network (DNN) for speech separation.